Timezone: »

Meta-Query-Net: Resolving Purity-Informativeness Dilemma in Open-set Active Learning
Dongmin Park · Yooju Shin · Jihwan Bang · Youngjun Lee · Hwanjun Song · Jae-Gil Lee

Thu Dec 01 02:00 PM -- 04:00 PM (PST) @ Hall J #709

Unlabeled data examples awaiting annotations contain open-set noise inevitably. A few active learning studies have attempted to deal with this open-set noise for sample selection by filtering out the noisy examples. However, because focusing on the purity of examples in a query set leads to overlooking the informativeness of the examples, the best balancing of purity and informativeness remains an important question. In this paper, to solve this purity-informativeness dilemma in open-set active learning, we propose a novel Meta-Query-Net (MQ-Net) that adaptively finds the best balancing between the two factors. Specifically, by leveraging the multi-round property of active learning, we train MQ-Net using a query set without an additional validation set. Furthermore, a clear dominance relationship between unlabeled examples is effectively captured by MQ-Net through a novel skyline regularization. Extensive experiments on multiple open-set active learning scenarios demonstrate that the proposed MQ-Net achieves 20.14% improvement in terms of accuracy, compared with the state-of-the-art methods.

Author Information

Dongmin Park (Korea Advanced Institute of Science and Technology)
Yooju Shin (Korea Advanced Institute of Science and Technology)
Jihwan Bang (NAVER)
Youngjun Lee (Korea Advanced Institute of Science & Technology)
Hwanjun Song (AWS AI Lab)
Jae-Gil Lee (Korea Advanced Institute of Science and Technology)

More from the Same Authors